Skip to content
memory-integration logo

Memory Integration

memory-integration

Use to maintain context across sessions - integrates episodic-memory for conversation recall and mcp__memory knowledge graph for persistent facts

SKILL.md

Full skill instructions

Memory Integration

Overview

Use both memory systems to maintain context across sessions.

Core principle: You have no memory between sessions. Use these tools to remember.

Systems:

  • Episodic Memory - Conversation history search
  • Knowledge Graph (mcp__memory) - Structured facts and relationships

When to Use Memory

MomentMemory Action
Session startSearch for relevant context
Before starting issueSearch for previous work
Making decisionCheck for past decisions
Completing workStore important learnings
Session endStore key outcomes

Episodic Memory

What It Stores

  • Full conversation history
  • Decisions made
  • Problems solved
  • Approaches tried
  • Lessons learned

Searching Episodic Memory

Use the episodic-memory skill or MCP tools:

Search for:
- Issue number: "issue 123", "#123"
- Feature name: "authentication", "user login"
- Problem type: "TypeScript error", "build failure"
- Project name: repository name
Semantic Search (Single Query)
// Search with natural language
mcp__plugin_episodic-memory_episodic-memory__search({
  query: "user authentication implementation decisions"
})
Precise Search (Multiple Concepts)
// Search for intersection of concepts
mcp__plugin_episodic-memory_episodic-memory__search({
  query: ["authentication", "session", "JWT"]
})
Reading Full Conversations

After finding relevant results:

// Read the full conversation
mcp__plugin_episodic-memory_episodic-memory__read({
  path: "/​path/​to/​conversation.jsonl"
})

What to Search For

SituationSearch Terms
Starting issue #123"issue 123", "#123"
Working on auth"authentication", "login", "session"
TypeScript problem"TypeScript", "type error", specific error message
Similar featureFeature name, related concepts

Knowledge Graph (mcp__memory)

What It Stores

  • Entities (Projects, Issues, Decisions, Patterns)
  • Relationships between entities
  • Observations about entities

Creating Entities

Store important facts:

// Create an entity for a project decision
mcp__memory__create_entities({
  entities: [{
    name: "Decision: Use JWT for Auth",
    entityType: "Decision",
    observations: [
      "Decided on 2024-12-01",
      "JWT chosen over sessions for API statelessness",
      "Related to issue #123",
      "Implementation in src/​auth/​jwt.ts"
    ]
  }]
})

Creating Relationships

Link entities together:

// Create relationships
mcp__memory__create_relations({
  relations: [
    {
      from: "Project: MyApp",
      to: "Decision: Use JWT for Auth",
      relationType: "has_decision"
    },
    {
      from: "Issue #123",
      to: "Decision: Use JWT for Auth",
      relationType: "resulted_in"
    }
  ]
})

Searching the Graph

// Search for relevant nodes
mcp__memory__search_nodes({
  query: "authentication"
})

// Open specific nodes
mcp__memory__open_nodes({
  names: ["Decision: Use JWT for Auth"]
})

// Read entire graph (for small graphs)
mcp__memory__read_graph({})

Memory Protocol

At Session Start

  1. Search episodic memory for:

    • Current issue number
    • Project/​repository name
    • Active feature being worked on
  2. Search knowledge graph for:

    • Project entity
    • Related decisions
    • Known patterns
  3. Synthesize context before proceeding

During Work

Store as you go:

EventStore In
Major decisionKnowledge graph entity
Problem solvedAdd observation to issue entity
Pattern discoveredKnowledge graph entity
Lesson learnedAdd observation

At Session End

  1. Update knowledge graph with:

    • New decisions made
    • Problems solved
    • Patterns discovered
  2. Add observations to existing entities:

    • Progress on issues
    • Learnings
    • Next steps

Entity Types

Suggested entity types for the knowledge graph:

TypeUse ForExample
ProjectRepository/​codebase"Project: MyApp"
IssueGitHub issues"Issue #123: Auth"
DecisionArchitectural decisions"Decision: Use JWT"
PatternCode patterns"Pattern: Repository Layer"
ProblemKnown issues"Problem: Race Condition in X"
PersonCollaborators"Person: Alice (maintainer)"

Example: Issue Memory Flow

Session 1: Starting Issue

// Search for any previous context
const episodic = await search("issue 456 user profile");
const graph = await search_nodes("user profile");

// If nothing found, create fresh entity
await create_entities({
  entities: [{
    name: "Issue #456: User Profile Page",
    entityType: "Issue",
    observations: [
      "Started: 2024-12-01",
      "Scope: Profile display, edit, avatar upload"
    ]
  }]
});

Session 1: Mid-Work Decision

// Store a decision made
await add_observations({
  observations: [{
    entityName: "Issue #456: User Profile Page",
    contents: [
      "Decision: Using react-image-crop for avatar cropping",
      "Reason: Best mobile support, active maintenance"
    ]
  }]
});

Session 2: Resuming

// Search for context
const results = await search("issue 456");
// Read: "Using react-image-crop for avatar cropping"

// Continue with context maintained

What to Store

Always Store

  • Architectural decisions with rationale
  • Non-obvious problem solutions
  • Important constraints discovered
  • Dependencies between components

Don't Store

  • Trivial implementation details
  • Things obvious from code
  • Temporary debugging notes
  • Speculation without conclusion

Checklist

At session start:

  • Search episodic memory for issue/​project
  • Search knowledge graph for context
  • Note relevant findings

During work:

  • Store major decisions
  • Record problem solutions
  • Note discovered patterns

At session end:

  • Update entities with progress
  • Add new learnings
  • Record next steps

Integration

This skill is called by:

  • session-start - Initial context gathering
  • issue-driven-development - Step 4

This skill supports:

  • Cross-session continuity
  • Decision documentation
  • Pattern discovery

More skills from majiayu000

xiaohongshu logo
majiayu000/claude-arsenal

xiaohongshu

xiaohongshu

286 148
View
agent-task-conductor logo
majiayu000/claude-skill-registry

agent-task-conductor

Conduct multi-agent task orchestration and workflow coordination.

663 1
View
conductor-setup logo
majiayu000/claude-skill-registry

conductor-setup

Initialize project with Conductor artifacts (product definition,

663 1
View
animation-designer logo
majiayu000/claude-skill-registry

animation-designer

Expert in web animations, transitions, and motion design using Framer Motion and CSS

663 1
View
diagramming logo
majiayu000/claude-skill-registry

diagramming

Creates Mermaid and ASCII diagrams for flowcharts, architecture, ERDs, state machines, mindmaps, and more. Use when user mentions diagram, flowchart, mermaid, ASCII diagram, text diagram, terminal diagram, visualize, C4, mindmap, architecture diagram, sequence diagram, ERD, or needs visual docume...

663 1
View
h3-pg logo
majiayu000/claude-skill-registry-data

h3-pg

PostgreSQL bindings for H3 hexagonal grid system. Use when working with H3 cells in Postgres, including spatial indexing, geometry/geography integration, and raster analysis.

23 1
View
conductor-development logo
majiayu000/claude-skill-registry

conductor-development

Context-Driven Development skill for projects using Conductor. Use this skill when you detect a `conductor/` directory in the project, when working on tasks defined in a `plan.md` file, or when the user asks about tracks, specs, or plans. Automatically applies TDD workflow, tracks task completion...

663 1
View
conductor-status logo
majiayu000/claude-skill-registry

conductor-status

Display project status, active tracks, and next actions

663 1
View
dockerization logo
majiayu000/claude-skill-registry

dockerization

Official Stakpak application containerization standard operating procedure, a step-by-step guidline to properly dockerize applications. This is a rule book curated by the Stakpak Team.

663 1
View

Popular AI tools

Kaiber logo
Video

Kaiber

Generate, edit, and beat-sync AI video with leading models in one workspace.

Paid
View
Vimcal logo
Productivity

Vimcal

The world's fastest calendar for remote work

Free
View

Transform Your Design with AI Designer by ImgCreator.ai

Freemium
View
Akool AI logo
Content & writing

Akool AI

Revolutionizing Video Production with AI-Powered Creativity

Paid
View

Extend an image past the frame and let AI fill the new aspect ratio.

Freemium
View
StarByFace logo
Security

StarByFace

Discover your celebrity doppelgänger with StarByFace!

Free
View
C

ChainClarity explains 700+ crypto whitepapers in plain English, with layered summaries, comparisons, research tools, alerts, and a $4.99 Pro plan.

Freemium
View
Opus Clip logo
Coding & apps

Opus Clip

Opus.ai: Revolutionize Your Web Experience

Free
View